Re: [PATCH v4 7/8] fuse: Add retry attempts for numa local queues for load distribution

[Luis Henriques <luis@igalia.com>]

On Mon, Apr 13 2026, Bernd Schubert via B4 Relay wrote:

> From: Bernd Schubert <bschubert@ddn.com>
>
> This is to further improve performance.
>
> fio --directory=/tmp/dest --name=iops.\$jobnum --rw=randread \
> --bs=4k --size=1G --numjobs=1 --iodepth=4 --time_based\
> --runtime=30s --group_reporting --ioengine=io_uring\
> --direct=1
>
> unpatched
>    READ: bw=650MiB/s (682MB/s)
> patched:
>    READ: bw=995MiB/s (1043MB/s)
>
> with --iodepth=8
>
> unpatched
>    READ: bw=641MiB/s (672MB/s)
> patched
>    READ: bw=966MiB/s (1012MB/s)
>
> Reason is that with --iodepth=x (x > 1) fio submits multiple async
> requests and a single queue might become CPU limited. I.e. spreading
> the load helps.
> ---
>  fs/fuse/dev_uring.c | 30 ++++++++++++++++++++++++++++--
>  1 file changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
> index ed061e239b8ed70ff36deb51dd6957fe1704ec87..e06d45b161d5000e24431314b2222b66bdea58aa 100644
> --- a/fs/fuse/dev_uring.c
> +++ b/fs/fuse/dev_uring.c
> @@ -19,6 +19,7 @@ MODULE_PARM_DESC(enable_uring,
>  
>  #define FUSE_URING_IOV_SEGS 2 /* header and payload */
>  
> +#define FUSE_URING_Q_THRESHOLD 2
>  
>  bool fuse_uring_enabled(void)
>  {
> @@ -1310,9 +1311,10 @@ static struct fuse_ring_queue *fuse_uring_select_queue(struct fuse_ring *ring,
>  						       bool background)
>  {
>  	unsigned int qid;
> -	int node;
> +	int node, retries = 0;
>  	unsigned int nr_queues;
>  	unsigned int cpu = task_cpu(current);
> +	struct fuse_ring_queue *queue, *primary_queue = NULL;
>  
>  	/*
>  	 *  Background requests result in better performance on a different
> @@ -1321,6 +1323,7 @@ static struct fuse_ring_queue *fuse_uring_select_queue(struct fuse_ring *ring,
>  	if (background)
>  		cpu++;
>  
> +retry:
>  	cpu = cpu % ring->max_nr_queues;
>  
>  	/* numa local registered queue bitmap */
> @@ -1336,12 +1339,35 @@ static struct fuse_ring_queue *fuse_uring_select_queue(struct fuse_ring *ring,
>  		qid = ring->numa_q_map[node].cpu_to_qid[cpu];
>  		if (WARN_ON_ONCE(qid >= ring->max_nr_queues))
>  			return NULL;
> -		return READ_ONCE(ring->queues[qid]);
> +		queue = READ_ONCE(ring->queues[qid]);
> +
> +		/* Might happen on teardown */
> +		if (unlikely(!queue))
> +			return NULL;
> +
> +		if (queue->nr_reqs < FUSE_URING_Q_THRESHOLD)
> +			return queue;
> +
> +		/* Retries help for load balancing */
> +		if (retries < FUSE_URING_Q_THRESHOLD) {
> +			if (!retries)
> +				primary_queue = queue;
> +
> +			/* Increase cpu, assuming it will map to a differet qid*/

nit: "different"

> +			cpu++;
> +			retries++;
> +			goto retry;
> +		}
>  	}
>  
> +	/* Retries exceeded, take the primary target queue */
> +	if (primary_queue)
> +		return primary_queue;
> +
>  	/* global registered queue bitmap */
>  	qid = ring->q_map.cpu_to_qid[cpu];
>  	if (WARN_ON_ONCE(qid >= ring->max_nr_queues))
> +	/* Might happen on teardown */

This comment should probably be in the line above the 'if' statement.

Cheers,
-- 
Luís

>  		return NULL;
>  	return READ_ONCE(ring->queues[qid]);
>  }
>
> -- 
> 2.43.0
>
>